devops-terraform-iac

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied infrastructure requirements to generate technical module definitions. This creates a potential surface where malicious instructions within those requirements could influence the agent's generated output.
  • Ingestion points: User-provided 'infrastructure requirements' described in Step 1 and the Contract section.
  • Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions embedded within the requirements.
  • Capability inventory: The skill is designed to produce IaC code and policy checklists but does not perform direct execution of commands like 'terraform apply' within this skill definition.
  • Sanitization: There are no instructions for sanitizing or escaping content provided in the requirements before they are incorporated into the infrastructure design.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 02:59 AM
Security Audit — agent-trust-hub — devops-terraform-iac